{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T10:16:57Z","timestamp":1783160217148,"version":"3.54.6"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201059"],"award-info":[{"award-number":["62201059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.inffus.2026.104408","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T23:07:19Z","timestamp":1776985639000},"page":"104408","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CCRDet: Cross-modal complementary region-aware framework for drone-based RGBT tiny person detection"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5956-3590","authenticated-orcid":false,"given":"Panzhe","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0229-8424","authenticated-orcid":false,"given":"Jue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1455-244X","authenticated-orcid":false,"given":"Tianyu","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0671-6777","authenticated-orcid":false,"given":"Guoqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3273-5522","authenticated-orcid":false,"given":"Liang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7747-523X","authenticated-orcid":false,"given":"Wenchao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.inffus.2026.104408_bib0001","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","article-title":"Pedestrian detection: an evaluation of the state of the art","volume":"34","author":"Dollar","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104408_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102246","article-title":"Improving RGB-infrared object detection with cascade alignment-guided transformer","volume":"105","author":"Yuan","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104408_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.102939","article-title":"Efficient multispectral object detection with attentive feature aggregation leveraging zero-shot implicit illumination guidance","volume":"118","author":"Xiong","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104408_bib0004","first-page":"1","article-title":"Illumination-Guided RGBT object detection with inter- and intra-modality fusion","volume":"72","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.inffus.2026.104408_bib0005","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.isprsjprs.2023.08.016","article-title":"Drone-based RGBT tiny person detection","volume":"204","author":"Zhang","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"issue":"2","key":"10.1016\/j.inffus.2026.104408_bib0006","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1109\/TIP.2016.2639450","article-title":"LIME: Low-light image enhancement via illumination map estimation","volume":"26","author":"Guo","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104408_bib0007","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"16794","article-title":"Large selective Kernel network for remote sensing object detection","author":"Li","year":"2023"},{"key":"10.1016\/j.inffus.2026.104408_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.inffus.2026.104408_bib0009","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"issue":"10","key":"10.1016\/j.inffus.2026.104408_bib0010","doi-asserted-by":"crossref","first-page":"17856","DOI":"10.1109\/TNNLS.2025.3586714","article-title":"An adaptive weighted metric learning network based on fractional domain decoupling for hyperspectral change detection","volume":"36","author":"Feng","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.inffus.2026.104408_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1222","article-title":"Perceptual generative adversarial networks for small object detection","author":"Li","year":"2017"},{"key":"10.1016\/j.inffus.2026.104408_bib0012","series-title":"IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium","first-page":"2483","article-title":"Deconv R-CNN for small object detection on remote sensing images","author":"Zhang","year":"2018"},{"key":"10.1016\/j.inffus.2026.104408_sbref0013","series-title":"Advances in Neural Information Processing Systems","article-title":"SNIPER: efficient multi-scale training","volume":"31","author":"Singh","year":"2018"},{"key":"10.1016\/j.inffus.2026.104408_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13668","article-title":"QueryDet: cascaded sparse query for accelerating high-resolution small object detection","author":"Yang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104408_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2965","article-title":"Region proposal by guided anchoring","author":"Wang","year":"2019"},{"key":"10.1016\/j.inffus.2026.104408_bib0016","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6054","article-title":"Scale-aware trident networks for object detection","author":"Li","year":"2019"},{"key":"10.1016\/j.inffus.2026.104408_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108998","article-title":"A full data augmentation pipeline for small object detection based on generative adversarial networks","volume":"133","author":"Bosquet","year":"2023","journal-title":"Pattern Recognit."},{"issue":"3","key":"10.1016\/j.inffus.2026.104408_bib0018","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","article-title":"Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges","volume":"22","author":"Feng","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.inffus.2026.104408_bib0019","series-title":"2021IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"7068","article-title":"ShapeConv: shape-aware convolutional layer for indoor RGB-D semantic segmentation","author":"Cao","year":"2021"},{"key":"10.1016\/j.inffus.2026.104408_bib0020","first-page":"1","article-title":"MultiSenseSeg: a cost-effective unified multimodal semantic segmentation model for remote sensing","volume":"62","author":"Wang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104408_bib0021","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"139","article-title":"Multimodal object detection via probabilistic ensembling","author":"Chen","year":"2022"},{"key":"10.1016\/j.inffus.2026.104408_bib0022","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.patcog.2018.08.005","article-title":"Illumination-aware faster R-CNN for robust multispectral pedestrian detection","volume":"85","author":"Li","year":"2019","journal-title":"Pattern Recognit."},{"issue":"12","key":"10.1016\/j.inffus.2026.104408_bib0023","doi-asserted-by":"crossref","first-page":"12680","DOI":"10.1109\/TCSVT.2025.3570466","article-title":"Cross-domain few-shot learning method based on fractional domain information for hyperspectral image multi-class change detection","volume":"35","author":"Feng","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104408_bib0024","first-page":"1","article-title":"Cross-domain few-shot learning based on decoupled knowledge distillation for hyperspectral image classification","volume":"62","author":"Feng","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104408_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109913","article-title":"ICAFusion: iterative cross-attention guided feature fusion for multispectral object detection","volume":"145","author":"Shen","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.inffus.2026.104408_bib0026","first-page":"1","article-title":"Transformer-based cross-Domain few-shot learning for hyperspectral target detection","volume":"63","author":"Feng","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104408_bib0027","series-title":"Computer Vision \u2013 ECCV 2020","first-page":"787","article-title":"Improving multispectral pedestrian detection by addressing modality imbalance problems","author":"Zhou","year":"2020"},{"key":"10.1016\/j.inffus.2026.104408_bib0028","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6364","article-title":"Rethinking multi-modal object detection from the perspective of mono-modality feature learning","author":"Zhao","year":"2025"},{"key":"10.1016\/j.inffus.2026.104408_bib0029","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5637","article-title":"Toward fast, flexible, and robust low-Light image enhancement","author":"Ma","year":"2022"},{"key":"10.1016\/j.inffus.2026.104408_bib0030","first-page":"251","article-title":"The dark side of CIELAB","author":"Sharma","year":"2012","journal-title":"Color Imaging Conf."},{"key":"10.1016\/j.inffus.2026.104408_bib0031","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.inffus.2026.104408_bib0032","first-page":"1","article-title":"C\u00b2Former: calibrated and complementary transformer for RGB-infrared object detection","volume":"62","author":"Yuan","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104408_bib0033","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8886","article-title":"Visible-thermal UAV tracking: a large-scale benchmark and new baseline","author":"Zhang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104408_bib0034","series-title":"Computer Vision \u2013 ECCV 2014","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.inffus.2026.104408_sbref0035","series-title":"Advances in Neural Information Processing Systems","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019"},{"key":"10.1016\/j.inffus.2026.104408_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.inffus.2026.104408_sbref0037","series-title":"Advances in Neural Information Processing Systems","first-page":"21002","article-title":"Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li","year":"2020"},{"key":"10.1016\/j.inffus.2026.104408_sbref0038","series-title":"Advances in Neural Information Processing Systems","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015"},{"key":"10.1016\/j.inffus.2026.104408_bib0039","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6154","article-title":"Cascade r-cnn: delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.inffus.2026.104408_bib0040","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.inffus.2026.104408_bib0041","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9627","article-title":"Fcos: fully convolutional one-stage object detection","author":"Tian","year":"2019"},{"key":"10.1016\/j.inffus.2026.104408_bib0042","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9756","article-title":"Bridging the gap between anchor-Based and anchor-free detection via adaptive training sample selection","author":"Zhang","year":"2020"},{"key":"10.1016\/j.inffus.2026.104408_bib0043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2022.3214929","article-title":"SSPNet: scale selection pyramid network for tiny person detection from UAV images","volume":"19","author":"Hong","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.inffus.2026.104408_bib0044","unstructured":"J. Wang, C. Xu, W. Yang, L. Yu, A normalized Gaussian wasserstein distance for tiny object detection, arXiv preprint arXiv: 2110.13389(2021)."},{"key":"10.1016\/j.inffus.2026.104408_bib0045","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"526","article-title":"RFLA: Gaussian receptive field based label assignment for tiny object detection","author":"Xu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104408_bib0046","unstructured":"F. Qingyun, H. Dapeng, W. Zhaokui, Cross-modality fusion transformer for multispectral object detection, arXiv preprint arXiv: 2111.00273(2021)."},{"key":"10.1016\/j.inffus.2026.104408_bib0047","series-title":"2023IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","first-page":"4159","article-title":"HRFuser: A multi-resolution sensor fusion architecture for 2D object detection","author":"Br\u00f6dermann","year":"2023"},{"key":"10.1016\/j.inffus.2026.104408_bib0048","doi-asserted-by":"crossref","first-page":"5082","DOI":"10.1109\/JSTARS.2025.3526995","article-title":"Transformer-based person detection in paired RGB-T aerial images with VTSar dataset","volume":"18","author":"Zhang","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104408_bib0049","first-page":"1","article-title":"IM-CMDet: an intramodal enhancement and cross-modal fusion network for small object detection in UAV aerial visible-Infrared imagery","volume":"63","author":"Luo","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104408_bib0050","series-title":"International Conference on Learning Representations","article-title":"How do vision transformers work?","author":"Park","year":"2022"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002873?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002873?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T09:30:32Z","timestamp":1783157432000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526002873"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":50,"alternative-id":["S1566253526002873"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104408","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CCRDet: Cross-modal complementary region-aware framework for drone-based RGBT tiny person detection","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104408","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104408"}}